def test_deltah(unspecified_test_corpus):
type_calls = [({'segment_pairs':[('s','ʃ')]},0.13333),
({'segment_pairs':[('m','n')]},0.13333),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.26667),]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription', 'type') as c:
for kwargs, v in type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
type_calls = [({'segment_pairs':[('s','ʃ')]},0.16667),
({'segment_pairs':[('m','n')]},0),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.16667)]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
token_calls = [({'segment_pairs':[('s','ʃ')]},0.24794),
({'segment_pairs':[('m','n')]},0.00691),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.25485),]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription', 'token') as c:
for kwargs, v in token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
token_calls = [({'segment_pairs':[('s','ʃ')]},0.25053),
({'segment_pairs':[('m','n')]},0),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.25053),]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'token', frequency_threshold = 3) as c:
for kwargs, v in token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
def test_deltah(unspecified_test_corpus):
type_calls = [({'segment_pairs':[('s','ʃ')]},0.02547695),
({'segment_pairs':[('m','n')]},0.02547695),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.05284),]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription', 'type') as c:
for kwargs, v in type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
type_calls = [({'segment_pairs':[('s','ʃ')], 'prevent_normalization':True},0.09953567),
({'segment_pairs':[('m','n')], 'prevent_normalization':True},0.09953567),
({'segment_pairs':[('e','o')], 'prevent_normalization':True},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')], 'prevent_normalization':True},0.206450877),]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription', 'type') as c:
for kwargs, v in type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
type_calls = [({'segment_pairs':[('s','ʃ')]},0.035015954),
({'segment_pairs':[('m','n')]},0),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.035015954)]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
token_calls = [({'segment_pairs':[('s','ʃ')]},0.08305),
({'segment_pairs':[('m','n')]},0.002314),
({'segment_pairs':[('e','o')]},0.0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.0853641),]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription', 'token') as c:
for kwargs, v in token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
def test_deltah_wordtokens(unspecified_discourse_corpus):
corpus = unspecified_discourse_corpus.lexicon
frequent_type_calls = [({'segment_pairs':[('s','ʃ')]},0.13333),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.26667),]
with MostFrequentVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in frequent_type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
frequent_type_calls = [({'segment_pairs':[('m','n')]},0),]
with MostFrequentVariantContext(corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in frequent_type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
frequent_token_calls = [({'segment_pairs':[('s','ʃ')]},0.24794),
({'segment_pairs':[('e','o')]},0),
({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.25485),]
with MostFrequentVariantContext(corpus, 'transcription', 'token') as c:
for kwargs, v in frequent_token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
frequent_token_calls = [({'segment_pairs':[('m','n')]},0),]
with MostFrequentVariantContext(corpus,
'transcription', 'token', frequency_threshold = 3) as c:
for kwargs, v in frequent_token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
count_token_calls = [({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.25483),
({'segment_pairs':[('m','n')]},0.00691),]
with SeparatedTokensVariantContext(corpus, 'transcription', 'token') as c:
for kwargs, v in count_token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
count_token_calls = [({'segment_pairs':[('s','ʃ')]},0.25053),
({'segment_pairs':[('e','o')]},0),]
with SeparatedTokensVariantContext(corpus,
'transcription', 'token', frequency_threshold = 3) as c:
for kwargs, v in count_token_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
relative_type_calls = [({'segment_pairs':[('m','n')]},0.13333),]
with WeightedVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in relative_type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
relative_type_calls = [({'segment_pairs':[('s','ʃ'),
('m','n'),
('e','o')]},0.16667),
({'segment_pairs':[('s','ʃ')]},0.16667),
({'segment_pairs':[('e','o')]},0),]
with WeightedVariantContext(corpus,
'transcription', 'type', frequency_threshold = 3) as c:
for kwargs, v in relative_type_calls:
assert(abs(deltah_fl(c, **kwargs)-v) < 0.0001)
def test_deltah_wordtokens(unspecified_discourse_corpus):
corpus = unspecified_discourse_corpus.lexicon
frequent_type_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.13333),
({
'segment_pairs': [('e', 'o')]
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.26667),
]
with MostFrequentVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in frequent_type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
frequent_type_calls = [
({
'segment_pairs': [('m', 'n')]
}, 0),
]
with MostFrequentVariantContext(corpus,
'transcription',
'type',
frequency_threshold=3) as c:
for kwargs, v in frequent_type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
frequent_token_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.24794),
({
'segment_pairs': [('e', 'o')]
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.25485),
]
with MostFrequentVariantContext(corpus, 'transcription', 'token') as c:
for kwargs, v in frequent_token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
frequent_token_calls = [
({
'segment_pairs': [('m', 'n')]
}, 0),
]
with MostFrequentVariantContext(corpus,
'transcription',
'token',
frequency_threshold=3) as c:
for kwargs, v in frequent_token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
count_token_calls = [
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.25483),
({
'segment_pairs': [('m', 'n')]
}, 0.00691),
]
with SeparatedTokensVariantContext(corpus, 'transcription', 'token') as c:
for kwargs, v in count_token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
count_token_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.25053),
({
'segment_pairs': [('e', 'o')]
}, 0),
]
with SeparatedTokensVariantContext(corpus,
'transcription',
'token',
frequency_threshold=3) as c:
for kwargs, v in count_token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
relative_type_calls = [
({
'segment_pairs': [('m', 'n')]
}, 0.13333),
]
with WeightedVariantContext(corpus, 'transcription', 'type') as c:
for kwargs, v in relative_type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
relative_type_calls = [
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.16667),
({
'segment_pairs': [('s', 'ʃ')]
}, 0.16667),
({
'segment_pairs': [('e', 'o')]
}, 0),
]
with WeightedVariantContext(corpus,
'transcription',
'type',
frequency_threshold=3) as c:
for kwargs, v in relative_type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
def test_deltah(unspecified_test_corpus):
type_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.13333),
({
'segment_pairs': [('m', 'n')]
}, 0.13333),
({
'segment_pairs': [('e', 'o')]
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.26667),
]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription',
'type') as c:
for kwargs, v in type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
type_calls = [({
'segment_pairs': [('s', 'ʃ')]
}, 0.16667), ({
'segment_pairs': [('m', 'n')]
}, 0), ({
'segment_pairs': [('e', 'o')]
}, 0), ({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.16667)]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription',
'type',
frequency_threshold=3) as c:
for kwargs, v in type_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
token_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.24794),
({
'segment_pairs': [('m', 'n')]
}, 0.00691),
({
'segment_pairs': [('e', 'o')]
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.25485),
]
with CanonicalVariantContext(unspecified_test_corpus, 'transcription',
'token') as c:
for kwargs, v in token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
token_calls = [
({
'segment_pairs': [('s', 'ʃ')]
}, 0.25053),
({
'segment_pairs': [('m', 'n')]
}, 0),
({
'segment_pairs': [('e', 'o')]
}, 0),
({
'segment_pairs': [('s', 'ʃ'), ('m', 'n'), ('e', 'o')]
}, 0.25053),
]
with CanonicalVariantContext(unspecified_test_corpus,
'transcription',
'token',
frequency_threshold=3) as c:
for kwargs, v in token_calls:
assert (abs(deltah_fl(c, **kwargs) - v) < 0.0001)
